> For the complete documentation index, see [llms.txt](https://perceptdot.gitbook.io/perceptdot/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://perceptdot.gitbook.io/perceptdot/readme.md).

# What is perceptdot? 👁️

perceptdot gives your AI agent **eyes** — it takes a screenshot of any website and tells you exactly what's broken.

Connect it to Claude Code or any MCP-compatible AI tool, and your agent can automatically detect layout bugs, overflowing elements, clipped text, and visual glitches — without you having to look.

***

## What it finds

✅ Buttons overflowing outside their container\
✅ Text getting clipped or cut off\
✅ Elements overlapping and hiding each other\
✅ Broken layouts and misaligned sections

***

## How it works

1️⃣ Your AI opens the website\
2️⃣ Takes a full-page screenshot (tiled at 1280×1600px)\
3️⃣ Analyzes each tile with Gemini 2.5 Flash\
4️⃣ Reports: *"The CTA button in section 3 overflows by 18px"*

***

## Two ways to use perceptdot

|                | MCP Server                           | GitHub Action       |
| -------------- | ------------------------------------ | ------------------- |
| **Best for**   | AI-assisted development              | CI/CD automation    |
| **Works with** | Claude Code, Cursor, Windsurf, Cline | Any GitHub workflow |
| **Trigger**    | Ask your AI                          | Every deployment    |
| **Setup**      | 1 command                            | \~10 lines of YAML  |

***

## Performance

* **5–20s** for a first scan (depends on page height)
* **\~0.3s** for cached results
* Supports **desktop** (1280px) · **tablet** (768px) · **mobile** (375px)

***

## Ready in 1 minute

Jump straight to setup 👉 [⚡ Quick Install](/perceptdot/install.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://perceptdot.gitbook.io/perceptdot/readme.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.